Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Jurnal Tekinkom (Teknik Informasi dan Komputer)

SISTEM PENUNJANG KEPUTUSAN PENERIMA PROGRAM KELUARGA HARAPAN DENGAN MENGGUNAKAN METODE TOPSIS Okta Jaya Harmaja; Maria Septina Hutauruk
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 3 No 2 (2020)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v3i2.134

Abstract

Currently poverty is still one of the problems faced by the people of Indonesia, based on data from the Central Statistics Agency (BPS), it is stated that the percentage of poor people in September 2019 was 9.22% or equivalent to 24.79 million people. One of the efforts that have been made by the Government to overcome the problem of poverty is the Family Hope Program (PKH). The program aims to break the chain or reduce the poverty index, increase human resources, and change behavior that is less supportive of improving the welfare of poor families. However, in its implementation there are still some problems that occur in the field, including the lack of a companion role, and some PKH recipients who are not on target, causing social suspicion. These problems can be overcome by using computer technology-based programs and still implementing transparent and accountable selection stages. In this study, the method used in the Decision Support System is the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method and the system is designed using the PHP programming language and MySQL database. With this program, it is hoped that the user as the PKH implementation committee can make data easier, determine quickly and efficiently and on target for determining recipients of PKH assistance.
ANALISIS TINGKAT KEPUASAN PELANGGAN PADA RUDANG HOTEL BERASTAGI MENGGUNAKAN METODE CUSTOMER SATISFACTION INDEX (CSI) Okta Jaya Harmaja; Windania Purba; Maxwell Paulus Siregar; Henry Triadi Manurung; Fransisco Andreas Sirait
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 5 No 1 (2022)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v5i1.511

Abstract

Service quality is very important in the hospitality industry because of the great competition in the industry. Therefore, the hotel must provide the best service to its guests. This study was conducted to see how the quality of service at the Rudang Berastagi hotel to guests using the CSI method to calculate the level of customer satisfaction at the Rudang Berastagi Hotel as an evaluation material to improve hotel services in the future. Data processing in this study was carried out using the Python programming language through Google Colab. Based on the calculation of guest satisfaction at Rudang Berastagi Hotel through a questionnaire of 110 respondents, it was found that the guests were satisfied with the services provided by Rudang Berastagi Hotel with a satisfaction level of 78.4% using the Customer Satisfication Index (CSI) method. According to the questionnaires that have been distributed, it is concluded that question number 1 with the contents of the questions having a complete, comfortable, clean, and well-organized room interior gets the highest mean value of 4.27%.
EVALUASI USABILITY TERHADAP SIAM UNPRI MENGGUNAKAN METODE HEURISTIC EVALUATION DAN USER TESTING br Bangun, Agita Putri; Octaviani, Vina; Pasaribu, Gres Audia; Harmaja, Okta Jaya
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.1976

Abstract

This study aims to assess the level of usability of the Student Academic Information System (SIAM) at Universitas Prima Indonesia (UNPRI) with a heuristic evaluation and user testing approach. Heuristic evaluation was conducted by three expert evaluators in the field of UI/UX and 21 problems were found during the trial process. Based on the results of heuristic evaluation testing, redesign and user testing of the redesign were carried out. Quantitative data obtained using the System Usability Scale (SUS) questionnaire, obtained a score of 80.5, which indicates that the redesigned system is in the “acceptable” category, but some improvements need to be made. Design improvement recommendations from these findings have been developed to improve the quality of system usage, especially SIAM UNPRI.
PERBANDINGAN ALGORITMA RANDOM FOREST DAN SUPPORT VECTOR MACHINES DALAM MEMPREDIKSI TINGKAT RISIKO SERANGAN JANTUNG BERDASARKAN KEBIASAAN MEROKOK Harmaja, Okta Jaya; Fernando, Fernando; Melati, Melati
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.1807

Abstract

Heart disease remains a major global health challenge, with smoking behavior identified as one of the most significant modifiable risk factors. This study aims to compare the performance of two machine learning algorithms—Random Forest and Support Vector Machine (SVM)—in predicting heart attack risk levels based on smoking habits and biometric indicators. Using a dataset of 3,901 subjects obtained from Kaggle, data preprocessing and feature engineering were conducted to optimize model accuracy. The SVM algorithm achieved an accuracy of 92.43%, with its best performance observed in the medium-risk category (precision: 0.95, recall: 0.97, F1-score: 0.96), although performance declined in low and high-risk categories. In contrast, the Random Forest algorithm demonstrated superior results, reaching 99.91% accuracy with perfect precision, recall, and F1-scores (1.00) across all risk categories. The findings indicate that Random Forest not only provides more consistent and accurate predictions but also minimizes classification errors effectively. This research suggests that Random Forest is a more reliable and robust approach than SVM for integrating into intelligent health information systems to support early detection and prevention strategies for heart disease, especially among individuals with active smoking behavior.